All activity
Suraj Vermastarted a discussion
Why we built enforcement OUTSIDE the AI model
Every AI safety tool today puts guardrails inside the model — prompt filtering, RLHF, Constitutional AI, output validation. They all share one flaw: if you trick the AI, the safety breaks too. In February 2026, Claude was jailbroken and 150GB of government data was stolen. GPT-5 was broken in 24 hours. Microsoft Copilot had a zero-click vulnerability that exfiltrated files without user...